Related papers: Security Evaluation of Pattern Classifiers under A…
Machine Learning models have been shown to be vulnerable to adversarial examples, ie. the manipulation of data by a attacker to defeat a defender's classifier at test time. We present a novel probabilistic definition of adversarial examples…
The convolutional neural network (CNN) architecture is increasingly being applied to new domains, such as malware detection, where it is able to learn malicious behavior from raw bytes extracted from executables. These architectures reach…
Neural networks have been proven to be vulnerable to a variety of adversarial attacks. From a safety perspective, highly sparse adversarial attacks are particularly dangerous. On the other hand the pixelwise perturbations of sparse attacks…
We investigate the feasibility of using a classifier for security-related requirements trained on requirement specifications available online. This is helpful in case different requirement types are not differentiated in a large existing…
When used in automated decision-making systems, machine learning (ML) models are vulnerable to data-manipulation attacks. Some defense mechanisms (e.g., adversarial regularization) directly affect the ML models while others (e.g., anomaly…
Deep learning models for image classification have become standard tools in recent years. A well known vulnerability of these models is their susceptibility to adversarial examples. These are generated by slightly altering an image of a…
Most state-of-the-art machine learning (ML) classification systems are vulnerable to adversarial perturbations. As a consequence, adversarial robustness poses a significant challenge for the deployment of ML-based systems in safety- and…
Deploying machine learning models in safety-critical domains poses a key challenge: ensuring reliable model performance on downstream user data without access to ground truth labels for direct validation. We propose the suitability filter,…
Since neural classifiers are known to be sensitive to adversarial perturbations that alter their accuracy, \textit{certification methods} have been developed to provide provable guarantees on the insensitivity of their predictions to such…
Physical adversarial attacks are increasingly studied in settings that resemble deployed surveillance systems rather than isolated image benchmarks. In these settings, person detection, multi-object tracking, visible--infrared sensing, and…
Evaluating robustness of machine-learning models to adversarial examples is a challenging problem. Many defenses have been shown to provide a false sense of robustness by causing gradient-based attacks to fail, and they have been broken…
The importance of security metrics can hardly be overstated. Despite the attention that has been paid by the academia, government and industry in the past decades, this important problem stubbornly remains open. In this survey, we present a…
Binary code similarity detection (BCSD) serves as a fundamental technique for various software engineering tasks, e.g., vulnerability detection and classification. Attacks against such models have therefore drawn extensive attention, aiming…
Deep neural networks are at the forefront of machine learning research. However, despite achieving impressive performance on complex tasks, they can be very sensitive: Small perturbations of inputs can be sufficient to induce incorrect…
Machine-learning models can be fooled by adversarial examples, i.e., carefully-crafted input perturbations that force models to output wrong predictions. While uncertainty quantification has been recently proposed to detect adversarial…
Adversarial transferability refers to the capacity of adversarial examples generated on the surrogate model to deceive alternate, unexposed victim models. This property eliminates the need for direct access to the victim model during an…
In this paper, we present a study that proposes a three-stage classifier model which employs a machine learning algorithm to develop an intrusion detection and identification system for tens of different types of attacks against industrial…
Simulating hostile attacks of physical autonomous systems can be a useful tool to examine their robustness to attack and inform vulnerability-aware design. In this work, we examine this through the lens of multi-robot patrol, by presenting…
Adversarial examples are input examples that are specifically crafted to deceive machine learning classifiers. State-of-the-art adversarial example detection methods characterize an input example as adversarial either by quantifying the…
This paper proposes a classification framework with a rejection option to mitigate the performance deterioration caused by adversarial examples. While recent machine learning algorithms achieve high prediction performance, they are…